Search Results - "Brockschmidt, Marc"

Analyzing Program Termination and Complexity Automatically with AProVE by Giesl, Jürgen, Aschermann, Cornelius, Brockschmidt, Marc, Emmes, Fabian, Frohn, Florian, Fuhs, Carsten, Hensel, Jera, Otto, Carsten, Plücker, Martin, Schneider-Kamp, Peter, Ströder, Thomas, Swiderski, Stephanie, Thiemann, René

“…In this system description, we present the tool AProVE for automatic termination and complexity proofs of Java, C, Haskell, Prolog, and rewrite systems. In…”
Get full text

Automatically Proving Termination and Memory Safety for Programs with Pointer Arithmetic by Ströder, Thomas, Giesl, Jürgen, Brockschmidt, Marc, Frohn, Florian, Fuhs, Carsten, Hensel, Jera, Schneider-Kamp, Peter, Aschermann, Cornelius

“…While automated verification of imperative programs has been studied intensively, proving termination of programs with explicit pointer arithmetic fully…”
Get full text

GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation by Brockschmidt, Marc

“…This paper presents a new Graph Neural Network (GNN) type using feature-wise linear modulation (FiLM). Many standard GNN variants propagate information along…”
Get full text

Exploring Representation of Horn Clauses using GNNs (Extended Technical Report) by Liang, Chencheng, Rümmer, Philipp, Brockschmidt, Marc

“…Learning program semantics from raw source code is challenging due to the complexity of real-world programming language syntax and due to the difficulty of…”
Get full text

HEAT: Hyperedge Attention Networks by Georgiev, Dobrik, Brockschmidt, Marc, Allamanis, Miltiadis

“…Learning from structured data is a core machine learning task. Commonly, such data is represented as graphs, which normally only consider (typed) binary…”
Get full text

Self-Supervised Bug Detection and Repair by Allamanis, Miltiadis, Jackson-Flux, Henry, Brockschmidt, Marc

“…Machine learning-based program analyses have recently shown the promise of integrating formal and probabilistic reasoning towards aiding software development…”
Get full text

SmartPaste: Learning to Adapt Source Code by Allamanis, Miltiadis, Brockschmidt, Marc

“…Deep Neural Networks have been shown to succeed at a range of natural language tasks such as machine translation and text summarization. While tasks on source…”
Get full text

Copy that! Editing Sequences by Copying Spans by Panthaplackel, Sheena, Allamanis, Miltiadis, Brockschmidt, Marc

“…Neural sequence-to-sequence models are finding increasing use in editing of documents, for example in correcting a text document or repairing source code. In…”
Get full text

Structured Neural Summarization by Fernandes, Patrick, Allamanis, Miltiadis, Brockschmidt, Marc

“…Summarization of long sequences into a concise statement is a core problem in natural language processing, requiring non-trivial understanding of the input…”
Get full text

Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamics by Klein, Leon, Foong, Andrew Y. K, Fjelde, Tor Erlend, Mlodozeniec, Bruno, Brockschmidt, Marc, Nowozin, Sebastian, Noé, Frank, Tomioka, Ryota

“…Molecular dynamics (MD) simulation is a widely used technique to simulate molecular systems, most commonly at the all-atom resolution where equations of motion…”
Get full text

Inferring Lower Runtime Bounds for Integer Programs by Frohn, Florian, Naaf, Matthias, Brockschmidt, Marc, Giesl, Jürgen

“…We present a technique to infer lower bounds on the worst-case runtime complexity of integer programs, where in contrast to earlier work, our approach is not…”
Get full text

Disentangling Interpretable Generative Parameters of Random and Real-World Graphs by Stoehr, Niklas, Yilmaz, Emine, Brockschmidt, Marc, Stuehmer, Jan

“…While a wide range of interpretable generative procedures for graphs exist, matching observed graph topologies with such procedures and choices for its…”
Get full text

Learning to Complete Code with Sketches by Guo, Daya, Svyatkovskiy, Alexey, Yin, Jian, Duan, Nan, Brockschmidt, Marc, Allamanis, Miltiadis

“…Code completion is usually cast as a language modelling problem, i.e., continuing an input in a left-to-right fashion. However, in practice, some parts of the…”
Get full text

Learning Units-of-Measure from Scientific Code by Danish, Matthew, Allamanis, Miltiadis, Brockschmidt, Marc, Rice, Andrew, Orchard, Dominic

“…CamFort is our multi-purpose tool for lightweight analysis and verification of scientific Fortran code. One core feature provides units-of-measure verification…”
Get full text

Learning to Represent Programs with Graphs by Allamanis, Miltiadis, Brockschmidt, Marc, Khademi, Mahmoud

“…Learning tasks on source code (i.e., formal languages) have been considered recently, but most work has tried to transfer natural language methods and does not…”
Get full text

Program Synthesis and Semantic Parsing with Learned Code Idioms by Shin, Richard, Allamanis, Miltiadis, Brockschmidt, Marc, Polozov, Oleksandr

“…Program synthesis of general-purpose source code from natural language specifications is challenging due to the need to reason about high-level patterns in the…”
Get full text

Analyzing Information Leakage of Updates to Natural Language Models by Zanella-Béguelin, Santiago, Wutschitz, Lukas, Tople, Shruti, Rühle, Victor, Paverd, Andrew, Ohrimenko, Olga, Köpf, Boris, Brockschmidt, Marc

“…To continuously improve quality and reflect changes in data, machine learning applications have to regularly retrain and update their core models. We show that…”
Get full text

Learning to Extend Molecular Scaffolds with Structural Motifs by Maziarz, Krzysztof, Jackson-Flux, Henry, Cameron, Pashmina, Sirockin, Finton, Schneider, Nadine, Stiefl, Nikolaus, Segler, Marwin, Brockschmidt, Marc

“…Recent advancements in deep learning-based modeling of molecules promise to accelerate in silico drug discovery. A plethora of generative models is available,…”
Get full text

Constrained Graph Variational Autoencoders for Molecule Design by Liu, Qi, Allamanis, Miltiadis, Brockschmidt, Marc, Gaunt, Alexander L

“…Graphs are ubiquitous data structures for representing interactions between entities. With an emphasis on the use of graphs to represent chemical molecules, we…”
Get full text

Generative Code Modeling with Graphs by Brockschmidt, Marc, Allamanis, Miltiadis, Gaunt, Alexander L, Polozov, Oleksandr

“…Generative models for source code are an interesting structured prediction problem, requiring to reason about both hard syntactic and semantic constraints as…”
Get full text